Ask HN: What Are You Working On? (August 2026)

I got laid off at the end of April and have been building my own personal dream tool since, it's a skeuomorphic carpentry simulator with an agent MCP. You start with real wood specs and a shop full of miter saws, router tables, table saws and the like. Think of it like Sketchup but no extruding rectangles.

It's been really fun to build with. Agents can create parametric procedures so e.g. stick framing becomes a simple function call for the next agent, building a flywheel. There is full agent-human parity in every surface, so there is a human UI for the procedures too.

Every operation is yaml, so agents pick it up pretty quickly. Agents can also file feature requests when they reach for a tool that doesn't exist. You can export to 3d printing files, video walk-through, step files, get a BOM and a cut plan, view your project in life-size with AR. There is a notion-like interface for authoring build guides... a lot going on. If you're a woodworker/software engineer you might enjoy it.

You can add the MCP to your agent of choice, send a picture, description, sketch or whatever; say "build this with Sawdust"

https://sawdust.diy

I’m working on a native UI framework in rust. I want to be able to build cross platform, fully native applications with native code. And I want platform native components.

I started with Leptos - which gives you a nice declarative UI syntax and reactive elements. I used Claude to get that working on iOS, cocoa and GTK. I made a nice little iOS schedule app for attendees at conferences. It works great. All rust, native UI and a fast and small binary. The current UI code is here: https://github.com/josephg/leptos-native (not officially part of leptos). It works well, but not all of the components I want have been implemented.

At the moment I’m rewriting the core to ditch the vibe coded parts and break the whole thing into an app backend API and separate platform layer. I want to be able to write apps in wasm and have a windows / mac / Linux host that can run them using native UI. And a runner to run any app using a TUI. And have a compilation process to compile the whole thing into a single native process for app developers and to publish to the App Store.

Releasing 3.3.0 version of my Video Hub App - https://github.com/whyboris/Video-Hub-App/ & https://videohubapp.com - 8+ years of development!

Working on 1.0.0 of Simple Image Browser - https://github.com/whyboris/Simple-Image-Browser

Releasing 2.0.0 of my Simplest File Renamer - https://github.com/whyboris/Simplest-File-Renamer - Electron to Tauri 130mb to 3mb

Releasing 1.0.0 of My Off Remote - https://github.com/whyboris/my-off-remote - turn off your PC from phone / tablet over WiFi

Lots of fun projects being listed. I'm working on Preloop(https://preloop.dev), a way to run your unmodified Github Actions locally or self-hosted in isolated cross-platform microvms(uses smolvm which uses libkrun vmm).I got frustrated with Github Actions reliability and inability to run or test my workflows locally so i re-wrote the runner and reverse-engineered the control plane so it follows the exact runner protocol the offficial runner does. Each job runs in a microvm that boots in 400ms from a packed image. Also supports a way to pause on every failure so you or your agent can immediately shell at that point, fix and retry(in a new environment) to verify. Also supports the full DAP protocol so you can interactively step/forward/investigate context at each step/job.

Try it out: https://github.com/preloopdev/preloop

I have been working on and off on https://www.whichtemple.in

- it is a collection of ~ 2700 temples across India, with images sourced from wikipedia

- it shows you a random temple each time you visit

- it has a map view of temples across India

So this is just the tip of the iceberg. I am trying to build a catalogue of all temples, starting with India, and expanding on to the rest of the world. The focus is on temples originating from Indic religions like Hinduism, Jainism and Buddhism.

I have personally discovered many cool temples that I have never heard of, but I am struggling on how to gamify this. Feedback welcome!

My two biggest projects are:

https://www.idlequest.net/ - a from-scratch recreation of the 1999 MMORPG classic EverQuest, featuring a real-time MMO server written in Go, a 3D game browser-based client built with Babylon.js, and the clasic UI recreated using React. You can play it both as a regular MMORPG but also in "idle mode" where it basically plays itself. This had up to 70 players online at once a while back which was really cool, though its popularity is in a bit of a lull right now. There are still tons of bugs and stuff that isn't fully implemented (and balance issues) but it's still fun for most people who have nostalgia for it.

https://www.newyokosuka.com/ - an unofficial Shenmue MMO experience. Based on the 1999 Sega Dreamcast game Shenmue, it's playable entirely in your browser! It's basic world exploration with forklift shenanigans, some basic dialogue systems, and a basic combat system test, but I'm about to push an update that includes all cutscenes and story progression as well. The story part is taking a bit of time because I'm having to mold it to fit in an MMO context. But it's a fun project to work on and the Shenmue community loves it so far.

I'm going whole-hog on LLM-driven development to build out an old-school FOSS forum that can run in resource-constrained environments with a minimum of fuss. Think phpBB but written in Rust with modern UI niceties and a SQLite backend. My hope is that interested parties will be able to deploy this on random SBCs or Unikraft and use cloudflared to expose their service to interested parties. Watching old forums that I used to frequent get gobbled up by VerticalScope makes me pine for the days of small self-hosted communities that existed for the hell of it instead of monetized interaction.

I'm (solo) spinning off the internal agent knowledge and observability layer used at Motion (YC W20, series C, ~40 devs). It was born out of a need to lift all devs using heterogeneous models, harnesses, and prompting styles to a higher level of consistency and quality while surfacing the visibility to see what's working and what's not. The knowledge layer is integrated into the code review layer and all of it tied together with telemetry to the document section level to see how each piece of context is affecting code generation.

Open source repo (.NET 10 + C# + Postgres): https://github.com/zeeq-ai/zeeq-app

Docs and more info: https://zeeq.ai

I'm building an AI agent that plays Slay the Spire. It currently reaches A20 Act 3 consistently and occasionally defeats the A20 Heart. It use two search: spare graph search for deck building, and MCTS for combat.

Parallelly, I'm working on an attention-based memory retrieval system that achieved SOTA on LongMemEval, LoCoMo, and code retrieval benchmarks. https://github.com/AttemorySystem/attemory/

Maybe later I'll build a live-streaming AI agent that plays Slay the Spire while conversing with viewers and remembering everything in chat!